ElevenLabs Expands AI Capabilities With Text-to-Sound Tool
ElevenLabs unveiled Sound Effects, an AI tool that generates customized audio samples from text descriptions. This tool offers creators a new way to enhance their projects with unique soundscapes.
- ElevenLabs launched Sound Effects, an AI tool that generates custom audio samples from textual descriptions, aiding content creators with efficient sound production.
- Partnering with Shutterstock, ElevenLabs leverages advanced AI models to deliver high-quality audio, with future plans for music generation and a voiceover studio.
ElevenLabs, an AI voice startup founded by former Google and Palantir employees, has introduced a new text-to-sound AI tool called Sound Effects. This addition follows the company’s earlier innovations in text-to-speech and speech-to-speech synthesis. This tool allows users to generate various audio samples by simply typing a description.
In February, The company teased the tool with clips featuring AI-enhanced sound effects. ElevenLabs collaborated with Shutterstock to bring this product to market, aiming for widespread adoption among content creators looking to enrich their projects with immersive soundscapes.
Currently, creators who need ambient noises for videos, games, or films must either record them manually or purchase them from online repositories. This can be costly and may not always yield the desired audio. The Sound Effects tool addresses this by enabling creators to generate specific sounds through text prompts. The model processes the input and generates six unique audio samples for the user to choose from. Users can then download or store their selected samples on the ElevenLabs platform.
See more: AMD Unveils New AI Chips in Bid To Disrupt NVIDIA’s Leadership
CEO Mati Staniszewski expressed hope that the tool will be widely used across various domains, including film, television, video games, marketing, and social media.
Looking ahead, the company plans to launch a music generation model and a voiceover studio offering, although timelines for these releases are not yet specified.